ABSTRACT
State-of-the-art supercomputers are made up of multiple types of resources. User jobs also have wide spectrum of resource requirements. Hence, a supercomputer can be thought of as a collection of heterogeneous resources with heterogeneous usage requirements from the users. Schedulers for such systems are challenged by several issues like scalability, GPU, topology and energy awareness. We view each scheduling step as solving a co-allocation problem, i.e. the problem of allocating multiple resources simultaneously to jobs. Collection of jobs can be repeatedly taken from the front of the job queue (i.e. a window of jobs) and a co-allocation problem formulated as an (integer) linear program (ILP/LP) can be solved. ILP formulations for single-type and multiple instances, a CPU-GPU and generalized systems are provided. Co-allocation solver is applied to both the window of jobs and the backfilled jobs. Simulation results show effectiveness of our approaches when compared with pure first-come-first-served schedulers.
Supplemental Material
Available for Download
- A. Haydar Özer, C. Özturan, A Model and Heuristic Algorithms for Multi-Unit Nondiscriminatory Combinatorial Auction, Computers and Operations Research, Vol. 36, p. 196--208, 2009. Google ScholarDigital Library
- George B. Dantzig, Discrete-Variable Extremum Problems, Operations Research Vol. 5, No. 2, April 1957, pp. 266--288Google ScholarDigital Library
- Parallel Workload Archive, http://www.cs.huji.ac.il/labs/parallel/workload/logs.htmlGoogle Scholar
- William TC Kramer, PERCU: A Holistic Method for Evaluating High Performance Computing Systems, Ph.D. thesis, EECS Department, University of California, Berkeley, Nov 2008.Google Scholar
- Y. Georgiou, Resource and Job Management in High Performance Computing, PhD Thesis, Joseph Fourier University, France, 2010Google Scholar
Index Terms
- Poster: co-allocation based scheduling for parallel systems
Recommendations
KOALA: a co-allocating grid scheduler
In multicluster systems, and more generally in grids, jobs may require co-allocation, that is, the simultaneous or coordinated access of single applications to resources of possibly multiple types in multiple locations managed by different resource ...
Mixed binary integer programming formulations for the reentrant job shop scheduling problem
This paper describes the development of mixed binary integer programming (BIP) formulations for the reentrant job shop scheduling problem. Based on an earlier classical job shop model developed by Manne and improved by Liao and You, this paper presents ...
Slot selection and co-allocation for economic scheduling in distributed computing
PaCT'11: Proceedings of the 11th international conference on Parallel computing technologiesIn this paper, we present slot selection algorithms for job batch scheduling in distributed computing with non-dedicated resources. Jobs are parallel applications and these applications are independent. Existing approaches towards resource co-allocation ...
Comments